Papers › Coherent Reconstruction of Multiple Humans from a Single Image

Coherent Reconstruction of Multiple Humans from a Single Image

15 Jun 2020CVPR 2020 6arXiv:2006.08586archive 2025-07-28

Wen Jiang, Nikos Kolotouros, Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis

In this work, we address the problem of multi-person 3D pose estimation from a single image. A typical regression approach in the top-down setting of this problem would first detect all humans and then reconstruct each one of them independently. However, this type of prediction suffers from incoherent results, e.g., interpenetration and inconsistent depth ordering between the people in the scene. Our goal is to train a single network that learns to avoid these problems and generate a coherent 3D reconstruction of all the humans in the scene. To this end, a key design choice is the incorporation of the SMPL parametric body model in our top-down framework, which enables the use of two novel losses. First, a distance field-based collision loss penalizes interpenetration among the reconstructed people. Second, a depth ordering-aware loss reasons about occlusions and promotes a depth ordering of people that leads to a rendering which is consistent with the annotated instance segmentation. This provides depth supervision signals to the network, even if the image has no explicit 3D annotations. The experiments show that our approach outperforms previous methods on standard 3D pose benchmarks, while our proposed losses enable more coherent reconstruction in natural images. The project website with videos, results, and code can be found at: https://jiangwenpl.github.io/multiperson

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its page in Syntology's graph, with its repositories and citations.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

JiangWenPL/multiperson mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Depth Estimation3D Human Reconstruction3D Pose Estimation3D ReconstructionInstance SegmentationPose EstimationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Depth Estimation Relative Human CRMH PCDR 54.83 #3 of 3 Archive leaderboard report
3D Depth Estimation Relative Human CRMH PCDR-Adult 55.47 #3 of 3 Archive leaderboard report
3D Depth Estimation Relative Human CRMH PCDR-Baby 34.74 #3 of 3 Archive leaderboard report
3D Depth Estimation Relative Human CRMH PCDR-Kid 48.37 #3 of 3 Archive leaderboard report
3D Depth Estimation Relative Human CRMH PCDR-Teen 59.11 #3 of 3 Archive leaderboard report
3D Depth Estimation Relative Human CRMH mPCDK 0.781 #3 of 3 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE B-MPJPE 140.3 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE B-MVE 142.2 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE B-NMJE 171.1 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE B-NMVE 173.4 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE F-MPJPE 54.5 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE F-MVE 50.2 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE FB-MPJPE 189.3 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE FB-MVE 191.8 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE FB-NMJE 230.9 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE FB-NMVE 233.9 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE LH/RH-MPJPE 46.4/46.0 #2 of 5 Archive leaderboard report
3D Human Reconstruction AGORA PIXIE LH/RH-MVE 49.5/49.0 #2 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections